Huy Vo
|
db91c4cf6c
|
hwacha
|
2012-07-27 18:13:20 -07:00 |
|
Huy Vo
|
32a16d183f
|
consts file doesn't depend on WIDTH_PVFB if HAVE_PVFB == false
|
2012-07-27 18:13:20 -07:00 |
|
Andrew Waterman
|
7778802395
|
reduce number of outstanding transactions
|
2012-07-26 14:51:41 -07:00 |
|
Yunsup Lee
|
3a2b305ddf
|
change htif width to 16
|
2012-07-25 17:25:50 -07:00 |
|
Andrew Waterman
|
177dbdadd9
|
merge HTIF port and backup memory port
|
2012-07-25 00:18:02 -07:00 |
|
Yunsup Lee
|
f4e3e72ad1
|
hoist HTIF_WIDTH out to consts
|
2012-07-23 17:30:04 -07:00 |
|
Huy Vo
|
04304fe788
|
moving util out into Chisel standard library
|
2012-06-06 12:51:26 -07:00 |
|
Huy Vo
|
181b20d69c
|
working vec unit with pvfb
|
2012-05-24 10:38:14 -07:00 |
|
Andrew Waterman
|
a2f6d01c1b
|
add programmable coreid register
|
2012-05-09 03:09:22 -07:00 |
|
Andrew Waterman
|
65ff397122
|
improved instruction decoding
it now makes use of don't-cares by performing logic minimization
|
2012-05-01 20:16:36 -07:00 |
|
Henry Cook
|
fef58f1b3a
|
Policy determined by constants. MSI policy added.
|
2012-04-11 17:56:59 -07:00 |
|
Andrew Waterman
|
c0ec3794bf
|
coherence mostly works now
|
2012-04-10 02:22:45 -07:00 |
|
Henry Cook
|
551e09c9d5
|
changed coherence type width names to represent max sizes for all protocols
|
2012-04-09 23:29:32 -07:00 |
|
Henry Cook
|
ed79ec98f7
|
Refactored coherence better from uncore hub, better coherence function names
|
2012-04-09 23:29:31 -07:00 |
|
Andrew Waterman
|
6bda8674bd
|
no dessert tonight :(
|
2012-03-26 23:50:09 -07:00 |
|
Yunsup Lee
|
e6b0e565de
|
turn HAVE_VEC on
|
2012-03-26 01:21:39 -07:00 |
|
Andrew Waterman
|
5f53cd4ac1
|
reduce HTIF width
|
2012-03-25 23:49:59 -07:00 |
|
Yunsup Lee
|
1f33f6bb58
|
HAVE_VEC is on
|
2012-03-24 20:54:43 -07:00 |
|
Andrew Waterman
|
86d56ff67b
|
refactor cpu/i$/d$ into Tile (rather than Top)
|
2012-03-24 16:57:28 -07:00 |
|
Andrew Waterman
|
54fa6f660d
|
new supervisor mode
|
2012-03-24 13:03:31 -07:00 |
|
Yunsup Lee
|
0edea00166
|
now HAVE_VEC is true, since it passes the emulator
|
2012-03-19 03:10:00 -07:00 |
|
Yunsup Lee
|
8c50c81b81
|
drop vec_irq_aux pcr register, now everything goes through badvaddr
|
2012-03-17 14:03:57 -07:00 |
|
Yunsup Lee
|
d38603a4ee
|
change number of tlb entries
|
2012-03-16 17:08:03 -07:00 |
|
Henry Cook
|
b5fa86e844
|
4-way associative by default
|
2012-03-14 17:51:12 -07:00 |
|
Yunsup Lee
|
b19d783fbd
|
add vector irq handler
|
2012-03-14 14:15:28 -07:00 |
|
Yunsup Lee
|
040d62f372
|
refactored vector exception handling interface
|
2012-03-13 23:45:34 -07:00 |
|
Yunsup Lee
|
5655dbd5da
|
add vvcfg and vtcfg instructions
|
2012-03-13 23:45:34 -07:00 |
|
Andrew Waterman
|
1788c34113
|
parameterize broadcast hub by # of tiles
|
2012-03-13 17:12:01 -07:00 |
|
Andrew Waterman
|
8ffdac9526
|
fix D$ store-upgrade bug
loads to the same address as stores that cause an upgrade
could return the old value
|
2012-03-10 15:50:10 -08:00 |
|
Yunsup Lee
|
44ff22a26f
|
vector exception handler now handles prefetches correctly
|
2012-03-10 12:54:36 -08:00 |
|
Yunsup Lee
|
a1b30282dd
|
major refactoring on vector exception interface
|
2012-03-09 01:09:22 -08:00 |
|
Andrew Waterman
|
941873bad1
|
coherence hub fixes
|
2012-03-07 21:03:44 -08:00 |
|
Andrew Waterman
|
499c5b4a2e
|
automatically infer MEM_TAG_BITS
|
2012-03-06 15:49:28 -08:00 |
|
Yunsup Lee
|
dba99e07a9
|
set MEM_TAG_BITS to 5 when HAVE_VEC is true, since NMSHR=4
|
2012-03-06 08:54:21 -08:00 |
|
Andrew Waterman
|
5f12990dfb
|
support memory transaction aborts
|
2012-03-06 00:35:02 -08:00 |
|
Yunsup Lee
|
d4ec7ff4d9
|
refined vector exception interface
|
2012-03-03 16:11:54 -08:00 |
|
Yunsup Lee
|
e28a551368
|
refactor code related to vector exceptions
- revisied interfaces
- new instructions
|
2012-03-03 15:15:00 -08:00 |
|
Henry Cook
|
1b3307df32
|
Removed has_data fields from all coherence messages, increased message type names to compensate
|
2012-03-02 23:51:53 -08:00 |
|
Yunsup Lee
|
1054cec087
|
add vec countq interface
|
2012-03-02 00:43:32 -08:00 |
|
Yunsup Lee
|
a8ef5e9e27
|
change NMSHR when HAVE_VEC is true
|
2012-03-01 01:07:47 -08:00 |
|
Yunsup Lee
|
6847160343
|
refactor arbiter priorities
|
2012-03-01 00:22:34 -08:00 |
|
Andrew Waterman
|
012da6002e
|
replace tile memory interface with ioTileLink
work in progress towards coherent HTIF. for now, requests
are incoherently passed through a null coherence hub.
|
2012-02-29 03:10:47 -08:00 |
|
Andrew Waterman
|
2b1c07c723
|
replace ioDCache with ioMem
|
2012-02-27 18:36:09 -08:00 |
|
Andrew Waterman
|
1d41a41afa
|
remove extraneous constants
|
2012-02-27 17:49:48 -08:00 |
|
Andrew Waterman
|
e12b9eae93
|
remove ext_mem interface
hindsight is 20/20
|
2012-02-26 18:53:39 -08:00 |
|
Yunsup Lee
|
f3bb02b2ea
|
refactored dmem arbiter
|
2012-02-26 17:38:08 -08:00 |
|
Daiwei Li
|
569698b824
|
dtlb now arbitrates between cpu, vec, and vec pf
|
2012-02-25 22:05:30 -08:00 |
|
Yunsup Lee
|
94ba32bbd3
|
change package name and sbt project name to rocket
|
2012-02-25 17:09:26 -08:00 |
|
Yunsup Lee
|
946e0c6e4e
|
add vector exception infrastructure
|
2012-02-25 16:37:56 -08:00 |
|
Andrew Waterman
|
4121fb178c
|
clean up mul/div interface; use VU mul if HAVE_VEC
|
2012-02-24 19:22:35 -08:00 |
|